Agent Data Tools: Everyday data

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: it discloses the pricing model ($0.003/call via x402 USDC or card key, first 25 free, failed calls free) and proactively reconciles the surprising readOnlyHint=false by stating 'Reads or computes only; not marked read-only because each call is charged.' This is exactly the context an agent needs and cannot infer from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the resource and returned fields, then usage, then pricing/auth. Dense but every clause carries information; the parenthetical price/auth sentence is long but earns its place for a paid tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by enumerating the return fields explicitly, including the population year. Combined with the pricing, auth, and read-only rationale, an agent has everything needed to decide and invoke correctly for a one-parameter open-world tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single parameter's schema description already says 'ISO 3166 alpha-2 or alpha-3 code', so the baseline is 3. The description adds the useful examples (SE, SWE, US) that concretely demonstrate both code formats, but no additional syntax, case, or validation semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Facts about a country by ISO code') and enumerates the exact fields returned: World Bank name, ISO-2/ISO-3 codes, region, income level, capital plus coordinates, and population with year. Nothing in the sibling list (earthquakes, weather, holidays, etc.) overlaps, and the source ('World Bank open data') is named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit intent ('Use to enrich records with country data') and a concrete invocation example ('country=SE'). It does not name when-not-to-use or an alternative tool, but the sibling set contains no competing country-data tool, so the omission is low-cost.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes well beyond the annotations: it discloses pricing ($0.003/call via x402 USDC or card key), the free tier (first 25 calls), the failed-call policy, and explicitly reconciles the readOnlyHint=false annotation by explaining that calls are charged. That is exactly the kind of behavioral context annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose, scope and filters before the pricing and annotation note, and nearly every clause carries information. It is a dense single paragraph with a slight pile-up of pricing detail, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by listing the return fields, and it covers source, time range, filters, cost model and the annotation rationale. An agent has everything needed to decide and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters (period, minMagnitude) and their allowed values are already documented in the schema. The description restates those values and adds an example, which is marginally useful but largely duplicative, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource and source (recent worldwide earthquakes from the USGS) and enumerates the returned fields (magnitude, place, time, depth, coordinates, tsunami flag, USGS link), so an agent knows exactly what it gets. It does not explicitly differentiate itself from siblings such as weather or time, but the resource is unique enough that confusion is unlikely.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states clear usage contexts ('Use for alerts, news and travel checks') and gives a concrete invocation example (period=day, minMagnitude=4.5). There are no explicit when-not conditions or named alternatives, which keeps it out of the top band.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=false and idempotentHint=false, and the description proactively explains the apparent discrepancy ('Reads or computes only; not marked read-only because each call is charged'). It also discloses cost ($0.003/call via x402 USDC or card key, first 25 free, failed calls free) and the CC0 data license. This is exactly the kind of context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose and return fields, then usage, then pricing. Every sentence carries information relevant to invoking the tool correctly. The pricing sentence is somewhat dense, but cost is a real decision input for an agent, so it earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description enumerates the returned fields (coordinates, description, country, admin region, population, elevation), covers cost/auth, and clarifies the read-only flag. Nothing material is missing for an agent to select and call this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds value by showing a worked example that pairs 'name' with 'count' (name=Uppsala, count=3), demonstrating how the two parameters interact. It doesn't restate range limits, but the schema already covers those.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (find places by name in Wikidata and return coordinates/description/country/region/population/elevation), plus the ordering guarantee ('best match first'). This clearly distinguishes it from sibling tools like weather, sun, or time, which are lookups that consume a location rather than resolve one.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use guidance: 'Use before weather, sun or distance lookups, or to tell two places of the same name apart.' It names the sibling tools it precedes and states the disambiguation use case. A concrete example (name=Uppsala, count=3) reinforces invocation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

It explains the otherwise confusing readOnlyHint=false by stating the tool 'reads or computes only' but is charged per call, and adds pricing/billing behavior (first 25 free, failed calls free, $0.003 via x402 USDC or card key). It does not account for openWorldHint=true or idempotentHint=false, so the read-only explanation is the main but not the only behavioral gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the resource and coverage, then usage, then commercial and safety notes in a logical order with no wasted sentences. It is a single dense paragraph, and the pricing detail is somewhat bulky for a tool description, but every clause carries information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the work of describing returns (date, local/English name, observed weekday) and the valid year window and country set. Pricing, safety posture and coverage are all present; only the openWorld/idempotency hints go unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and both parameters are already documented there, including the country code list and the year range/default. The description adds only a redundant example, correcting nothing beyond confirming the effective 2024-2100 window, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (nationwide public holidays) with explicit coverage (US federal, UK England and Wales, SE, DE, FR, NO, DK, FI) and enumerates the returned fields (date, local and English name, observed weekday). This clearly separates it from siblings like country, time, sun and moon.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete use contexts (scheduling, delivery dates, business-day maths) plus a worked example (country=SE, year=2026), which is enough to place the tool. It stops short of stating when NOT to use it or naming a sibling alternative (e.g., time or country) for non-holiday date needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well past the annotations: pricing ($0.003/call via x402 USDC or card key), first 25 free, failed calls free, local computation, and an explicit rationale for why readOnlyHint is false (each call is charged). It also clarifies the tricky 'local compute vs remote read' and billing-on-failure semantics an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the returned values, then usage, then example, then billing. Dense but every clause carries a distinct fact; the pricing sentence is long but necessary for a paid tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description fully enumerates the return fields and the extra next-new/full-moon values, so an agent knows exactly what it gets. Cost and free-tier terms complete the picture for invocation decisions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% — the single date parameter already documents 'Date or ISO time (default now)'. The description adds only an example value and the UTC framing, which is consistent with the baseline 3 when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Begins with the exact payload — phase name, illuminated percentage, age in days, plus next new and full moon (UTC) — and states the computation method (mean synodic month). It is unambiguous against siblings like sun, time, or holidays.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use for calendars and night-sky planning" plus a concrete example (date=2026-10-18) gives clear context for invocation. It stops short of naming alternatives or exclusions, e.g. when to prefer the sun tool for a combined sky-planning query.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: it discloses pricing ($0.003/call via x402 USDC or card key, first 25 free, failed calls free) and explicitly reconciles the counterintuitive readOnlyHint=false by explaining the call is charged even though it 'reads or computes only'. That is exactly the kind of context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then usage, then pricing/auth caveats — no sentence is wasted. The 'Example: package=hono' fragment is mildly redundant with the schema's own example, keeping it just under top marks.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description does convey the returned shape (counts for day/week/month) plus auth and billing prerequisites. It omits any mention of error/rate-limit behavior, but for a single-parameter read tool this is close to complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single parameter is already documented with a format example in the schema ('react or @scope/name'). The description's 'Example: package=hono' adds a concrete case but no new syntax or constraint, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (download counts of an npm package), the exact time granularities returned (last day, week, month), and the data source (official npm registry API). The 'npm' qualifier cleanly separates it from the sibling pypi tool without needing to name it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use to judge how widely a dependency is used' gives a clear context for when to reach for it, and the npm scope implicitly routes Python-package lookups elsewhere. It stops short of naming the pypi sibling as the explicit alternative, so it is clear-but-not-exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With readOnlyHint=false on an operation that only reads, the description preempts confusion by stating 'Reads or computes only; not marked read-only because each call is charged.' It also discloses pricing ($0.003/call, first 25 free, failed calls free) and the payment paths (x402 USDC or card key via /credits), which the annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

What the tool returns is front-loaded, followed by usage, an example, cost model, and the annotation rationale. Every sentence carries information an agent needs, with no redundant restatement of the name or title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description compensates by enumerating the returned fields. Combined with the usage cue, example value, and full cost/payment disclosure, an agent has everything required to invoke it correctly and predict the charge.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single parameter, so the schema already defines its meaning. The description adds a concrete worked example ('package=requests') that clarifies the expected value format, a modest but real increment over the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (a Python package on PyPI) and enumerates exactly what is returned: latest version, summary, licence, required Python version, home page, release date and release count. That field list makes it immediately distinguishable from ecosystem-adjacent siblings like npm_downloads, without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear usage context — 'Use to check a dependency before installing it' — which tells the agent when this tool is the right pick. There is no explicit when-not guidance or naming of alternative tools, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond annotations: discloses the pricing model ($0.003/call via x402 USDC or card key, first 25 free, failed calls free), that no outside service is used, and that polar day/night is handled. Crucially it explains the unusual readOnlyHint=false annotation ('each call is charged'), resolving a contradiction an agent would otherwise have to guess at.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with what is computed, followed by edge cases, use cases, example, then cost. Dense but every clause earns its place; the pricing sentence is long but necessary given the annotation rationale it supports.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description still enumerates the returned quantities (sunrise, sunset, solar noon, civil dawn/dusk, day length) and their UTC basis. Edge-case handling, cost, and auth path are all covered, leaving nothing essential for a correct invocation unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the three parameters are already documented, putting the baseline at 3. The description adds an end-to-end worked example that shows valid lat/lon/date values together and confirms output timezone is UTC, which is real practical value above the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb+resource ('Sunrise, sunset, solar noon, civil dawn and dusk (UTC) and day length') and scopes it to any place/date. An agent can distinguish it from siblings like moon, time, and weather without opening schemas, and the stated computation method ('standard solar equations') pins the semantics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit use cases ('photography, events and outdoor planning') and a concrete worked example (lat=59.33, lon=18.07, date=2026-12-21) give clear context. However, no sibling alternatives are named (e.g. when to prefer moon or time instead), so the routing guidance is contextual rather than exclusionary.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes beyond the annotations by explaining the surprising readOnlyHint=false: 'Reads or computes only; not marked read-only because each call is charged.' It also discloses pricing ($0.002/call via x402 USDC or card key, first 25 free, failed calls free) and that DST is handled — behavioral context an agent cannot derive from the annotation block.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core capability, then optional conversion, then usage, then an example, then commercial terms — a sensible ordering. Dense but each sentence carries information; the pricing sentence is long but materially affects whether an agent should call it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by naming the returned fields (UTC offset, weekday, abbreviation, Unix timestamp). With only three params, one required, plus the example and pricing, an agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3, but the description adds a concrete worked example (zone=Europe/Stockholm, at=2026-03-01T09:00:00+01:00, to=America/New_York,Asia/Tokyo) demonstrating format and comma-separated multi-zone usage. It also notes the 'max 10' and default-to-now semantics, adding real value over the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'the exact current date and time in any IANA time zone' plus optional conversion into up to 10 other zones. The return payload is enumerated (UTC offset, weekday, abbreviation, Unix timestamp), which no sibling (sun, moon, holidays) offers, so the agent can distinguish it immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names three triggering scenarios: needing to know the current time, scheduling a meeting across time zones, and converting a timestamp to local time. No when-not guidance or named alternative is given, but the sibling set makes the boundary obvious, so this stops just short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations and even explains an anomaly in them: 'Reads or computes only; not marked read-only because each call is charged' directly resolves why readOnlyHint=false on a non-mutating tool. It also discloses data provenance (Norwegian Meteorological Institute), cost model ($0.002/call via x402 USDC or card key, first 25 free, failed calls free) and that the tool is not idempotent in practice because each call bills.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and return contents are front-loaded, then provenance, use cases, example, and pricing in a sensible order; every sentence is a short clause rather than prose. The pricing/auth sentence is longer than strictly needed for tool selection, which keeps it from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so by enumerating every field and the forecast horizon. Cost, auth path, data source, and failure billing are all covered; only minor items (forecast timezone/reference time, error semantics beyond 'failed calls free') are absent for a 3-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, and the description adds real value on top: a worked example (lat=59.33, lon=18.07, hours=12) showing how the three parameters combine, plus output units (Celsius, mm) that the schema does not state. It does not add further syntax or bounds beyond the schema's 1-48 default 12, so it is not a full 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb+resource ('Weather for any point on Earth by latitude and longitude') and enumerates exactly what is returned: temperature in Celsius, conditions, precipitation, wind, humidity, cloud cover, pressure, plus an hourly forecast up to 48h. Nothing in the sibling set (sun, moon, time, geocode, earthquakes) overlaps, and the distinction is obvious from the text alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear application context ('travel and event planning, logistics, agriculture and any agent that needs the weather'), which tells the agent when this is the right tool. It stops short of explicit exclusions or naming alternatives (e.g., sun/moon for astronomical data), so it lands at clear-context-no-exclusions rather than full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.